ez_listening.py

import sys
import speech_recognition as sr
import pyttsx3 as lst
import winsound
from colorama import init

# Created by "Muhammad Wildan Aldiansyah"
# Currently on development
# Simple Text to Speech, especially imitate your voice 

init() # Colorama init..
engine = lst.init() # Declare Text to Speech object as Engine

class colors:
    HEADER = '\033[95m'
    BLUE = '\033[94m'
    GREEN = '\033[92m'
    YELLOW = '\033[93m'
    RED = '\033[91m'
    ENDC = '\033[0m'
    BOLD = '\033[1m'
    UNDERLINE = '\033[4m'

class languages:
    lg = ["id-ID", "de-DE", "en-GB", "en-US", "jv-ID"] # List of available languages
    number = 0 

    # Indonesia
    # Germany
    # English British
    # English US
    # Javanese

    def choose_language(self): # Method for return languages
        return self.lg[self.number]

lang = languages() # Declare languages
values = str(lang.choose_language()) # Get string formatted language as values 

def beeping():
    frequency = 2500  # Set Frequency 2500 Hz
    duration = 500  # Set Duration to 500 ms == 0.5 second
    winsound.Beep(frequency, duration) # Windows start to beeping as Frequency and Duration

def text_to_speech(text):
    engine.say(text) # Text to speech do say something as text
    engine.runAndWait() # Runs an event loop till all queued completed

def setting_rate_speech():
    rate = engine.getProperty('rate') # Get default rate from engine
    engine.setProperty('rate', rate) # Set property of rate for Text to speech

def input_text_from_speech():
    recog = sr.Recognizer() # Init recog as Speech Recognition's recognizer
    with sr.Microphone() as source: 
        audio = recog.listen(source) # Get voice from microphone then save to audio as values 

        try:
            text = recog.recognize_google(audio, language=values) # Get text from what you have been spoken
            print('Said : {} ' . format(text)) # Print the formatted result of text by google recognizer 
            setting_rate_speech()
            text_to_speech(text)
        except:
            beeping()
            text =  colors.RED + 'Said : Sorry can\'t recognize your voice' + colors.ENDC
            print(text)

    engine.stop() # Stop the engine and clearing all queued event

def main():
    condition = True
    while condition: # Infinite loop for main method
        input_text_from_speech()
        condition = False
    return main()

if __name__ == "__main__":
    if(len(sys.argv) == 1):
        print(colors.RED + 'Please input the argument. ex : python ez_listening.py 1, Exit..' + colors.ENDC)
        exit
    else:
        if(sys.argv[1].isdigit()):
            if(int(sys.argv[1]) >= 0 and int(sys.argv[1]) <= 4):
                lang.number = int(sys.argv[1])
                txt = colors.HEADER + 'Language chosen is ' + lang.choose_language() 
                txt += "\n" + 'Speech Now ...' + colors.ENDC
                txt += "\n---------------------------------------------------"
                print(txt)
                main()
            else:
                print(colors.RED + 'Only values between 0 - 4 are accepted, Exit..' + colors.ENDC)
                exit
        else:
            print(colors.RED + 'Please input the correct argument only number will be accepted, Exit..' + colors.ENDC)
            exit